© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240864
    Prev
    Next
    INDEX
    Explanations

    unfinished objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Verantwortung
    0.59
     канторы
    0.57
    axiom
    0.56
     Bestellung
    0.52
     Perspekt
    0.50
     काढ
    0.50
    ⺆
    0.49
     Direktor
    0.49
     পদ্ধ
    0.49
     Prakt
    0.49
    POSITIVE LOGITS
    .\
    0.51
    _
    0.49
    {
    0.49
    ח
    0.49
    /
    0.49
     rect
    0.48
    ...
    0.46
    ơ
    0.46
    Ses
    0.46
    á
    0.45
    Activations Density 0.001%

    No Known Activations